-
Currently, the individual pages that come from the processing pipeline end up being much worse in quality than what they look like in the original, source PDF files.
-
See tools developped by @ONEcampaign, @jm-rivera, @lpicci96 team:
https://github.com/ONEcampaign/bblocks/blob/main/bblocks/import_tools/imf_weo.py
-
### Feature request
Currently, Weaviate vectorstore doesn't provide option for updation of vector embeddings on existing index and deletion of index.
### Motivation
This feature request is related …
-
Instead of passing header and footer in the command line parameters, I wonder if it's possible to have them embedded in the html source page.
The benefit would be to have a single html page with one …
-
Similar to the work that's happening in #286, where we can attach image files, I'd like to be able to attach arbitrary file types and be able to then include them in the context of the chat. Eventual…
-
Thank you for the great work and it is prominent! Previously I used Google Vertex AI (i.e. Gemini) for doing something similar to yours but this repository is way better than mine.
It would be gre…
-
Since some versions of PyPDF2, the pdf documents that I split and regenerate are loosing PDF/A confirmation (checked with https://avepdf.com/pdfa-validation). Those documents are not accepted by certa…
-
I am experiencing issue frequently with exception occurring during Extract only of a PDF document. Here is the solr response:
500
6854
org.apache.solr.common.SolrException
…
-
To make manual entry of statement items easier for users, the following is suggested,
- [ ] Implement key combinations to navigate and control statement item rows
- [ ] Filter out sections and ana…
-
**Description:**
I'm encountering an issue with my Flask application where I'm unable to retrieve a response from the bot when sending a query through the index.html page. Here are the details:
**…